MétaCan
Menu
Back to cohort
Record W4205726258 · doi:10.1109/cog52621.2021.9619156

Sneak-Attacks in StarCraft using Influence Maps with Heuristic Search

2021· article· en· W4205726258 on OpenAlex
Lucas Critch, David G. Churchill

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venue2021 IEEE Conference on Games (CoG) · 2021
Typearticle
Languageen
FieldComputer Science
TopicArtificial Intelligence in Games
Canadian institutionsMemorial University of Newfoundland
Fundersnot available
KeywordsAdversaryComputer scienceHeuristicSurpriseArtificial intelligenceComputer securityCommunication

Abstract

fetched live from OpenAlex

Real-Time Strategy (RTS) games have consistently been popular among AI researchers over the past couple of decades due to their complexity and difficulty to play for both humans and AI. A popular strategy in RTS games is a “Sneak-Attack,” where one player tries to maneuver some of their units into the base of their enemy without being seen for as long as possible to surprise their enemy and deal massive damage to their economy. This paper introduces a novel method for finding sneak-attack paths in StarCraft by combining influence maps with heuristic search. The combined system creates paths that can guide units effectively - and automatically - into the enemy's base by avoiding enemy unit vision and minimizing both travel distance and unit damage. Our results show that our new system performs better than direct paths across a variety of maps in terms of total transport deaths, total damage taken, as well as the total time spent by the transport within enemy vision. We then utilize this new system to demonstrate a proof of concept for calculating building placements to defend against enemy sneak-attacks.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.458
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.072
GPT teacher head0.324
Teacher spread0.251 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it